Shaun Kotek 90512b2e8b fix: Use iterator as not to store all the file loads in memory at once (#36149) ...

Signed-off-by: Shaun Kotek - Nvidia <skotek@nvidia.com>

2026-03-08 20:25:21 -07:00

..

reload

…

__init__.py

…

base_loader.py

…

bitsandbytes_loader.py

[Hardware] Replace torch.cuda.empty_cache with torch.accelerator.empty_cache (#30681)

2026-03-04 09:49:47 +00:00

default_loader.py

Revert "[Misc] Enable weights loading tracking for quantized models" (#35309)

2026-02-25 09:20:15 -08:00

dummy_loader.py

…

gguf_loader.py

…

runai_streamer_loader.py

…

sharded_state_loader.py

…

tensorizer_loader.py

…

tensorizer.py

…

utils.py

[Feature] Support CPU Offloading without Pytorch Pinned Memory that leads to doubled allocation (#32993)

2026-02-13 08:11:26 -08:00

weight_utils.py

fix: Use iterator as not to store all the file loads in memory at once (#36149)

2026-03-08 20:25:21 -07:00